© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 5234
    Prev
    Next
    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     démocr
    -0.58
     OFDb
    -0.56
    ViewImports
    -0.56
    <>());
    -0.54
    fortawesome
    -0.54
     immédi
    -0.52
     IMMEDIATE
    -0.50
    vodu
    -0.49
     LIABLE
    -0.48
    ))=\
    -0.48
    POSITIVE LOGITS
    homonymie
    0.65
     itself
    0.62
     ourselves
    0.60
     yourselves
    0.57
     yourself
    0.54
    يميديا
    0.54
     himself
    0.52
    pch
    0.52
     themselves
    0.50
    himself
    0.50
    Activations Density 0.005%

    No Known Activations